Deep Reinforcement Learning for Algorithmic Trading

24 Pages Posted: 10 Apr 2021

See all articles by Álvaro Cartea

Álvaro Cartea

University of Oxford; University of Oxford - Oxford-Man Institute of Quantitative Finance

Sebastian Jaimungal

University of Toronto - Department of Statistics

Leandro Sánchez-Betancourt

King's College London

Date Written: March 25, 2021

Abstract

We employ reinforcement learning (RL) techniques to devise statistical arbitrage strategies in electronic markets. In particular, double deep Q network learning (DDQN) and a new variant of reinforced deep Markov models (RDMMs) are used to derive the optimal strategies for an agent who trades in a foreign exchange (FX) triplet. An FX triplet consists of three currency pairs where the exchange rate of one pair is redundant because, by no-arbitrage, it is determined by the exchange rates of the other two pairs. We use simulations of a co-integrated model of exchange rates to implement the strategies and show their financial performance.

Keywords: reinforcement learning, machine learning, algorithmic trading, foreign exchange, triplets

Suggested Citation

Cartea, Álvaro and Jaimungal, Sebastian and Sánchez-Betancourt, Leandro, Deep Reinforcement Learning for Algorithmic Trading (March 25, 2021). Available at SSRN: https://ssrn.com/abstract=3812473 or http://dx.doi.org/10.2139/ssrn.3812473

Álvaro Cartea

University of Oxford ( email )

Mansfield Road
Oxford, Oxfordshire OX1 4AU
United Kingdom

University of Oxford - Oxford-Man Institute of Quantitative Finance ( email )

Eagle House
Walton Well Road
Oxford, Oxfordshire OX2 6ED
United Kingdom

Sebastian Jaimungal

University of Toronto - Department of Statistics ( email )

100 St. George St.
Toronto, Ontario M5S 3G3
Canada

HOME PAGE: http://http:/sebastian.statistics.utoronto.ca

Leandro Sánchez-Betancourt (Contact Author)

King's College London ( email )

Strand
London, England WC2R 2LS
United Kingdom

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
1,269
Abstract Views
2,556
rank
22,075
PlumX Metrics